Method for predicting uplift bearing capacity of suction bucket

Abstract

The invention provides a method for predicting the uplift bearing capacity of a suction bucket. The method comprises the following steps: establishing a visual experiment device for uplift of a suction anchor; carrying out suction anchor up-pull experiments under different working conditions, and obtaining a relation curve of up-pull tension along with displacement change under different working conditions through data processing; generating a'factor-uplift force 'database of the suction bucket; a BP-RF machine learning algorithm is selected to carry out small sample data prediction; and comparing and analyzing the prediction result and the actual measurement result, and judging the influence rule of the uplift force. According to the method, limitation of experimental devices and conditions is considered, the BP-RF hybrid machine learning method is established by aiming at a small sample database and integrating advantages of a BP neural network algorithm and an RF algorithm for processing a small sample problem, a suction bucket uplift bearing capacity prediction model is established based on the method, and the prediction accuracy of the uplift bearing capacity of the suction bucket is improved. Therefore, the influence rule of the length, the diameter and the uplift rate of the suction bucket on the uplift bearing capacity is comprehensively and accurately evaluated, and a reference is provided for the design of the uplift bearing capacity of the suction bucket.

Description

Technical Field

[0001] The invention relates to the technical field of suction bucket foundations, and in particular to a method for predicting the pull-out bearing capacity of a suction bucket. Background Art

[0002] Offshore wind farms will develop in deeper waters in the future, and floating wind turbines are an inevitable choice for future development. Offshore wind power will inevitably move from offshore to offshore, from shallow sea to deep sea. Floating wind turbines are connected to deep-sea suction anchors through anchor chains to withstand the pull-out force caused by wind and waves. The marine environment is complex and changeable, often accompanied by severe typhoons and complex sea conditions. When a storm surge comes, the overturning moment of the offshore wind power foundation is large, and the corresponding anchor cable transmits a large pull-out force to the suction anchor. Therefore, it is very necessary to study and determine the pull-out limit bearing capacity of the suction anchor, which provides a theoretical basis for the installation and design of wind power foundations in the deep sea. It is of considerable engineering significance to study the mechanical properties of deep-sea suction anchors under storm surges. Although a lot of research has been done on the pull-out bearing characteristics of water-absorbing anchors, few people have focused on studying the deformation of the soil inside and outside the suction anchor during the pull-out process. Moreover, the pull-out rate is very slow when conducting a suction anchor pull-out experiment in sand, and most of them are studies on the bearing characteristics of the suction anchor under static load. There is little research on the uplift bearing characteristics under high-speed loads, especially under completely undrained conditions. Summary of the invention

[0003] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and provide a method for predicting the pull-out bearing capacity of a suction anchor, so that the influence of the suction bucket length, diameter and pull-out rate on the pull-out bearing capacity can be studied.

[0004] To achieve the above object, the present invention proposes a method for predicting the pull-out bearing capacity of a suction bucket, comprising the following steps:

[0005] S1: Establish a visual experimental device for suction anchor pull-out;

[0006] S2: Using the experimental device, the suction anchor pull-out test under different working conditions is carried out, and the relationship curve between the pull-out force and the displacement under different working conditions is obtained through data processing;

[0007] S3: Generate a suction bucket "factor-pull force" database based on the relationship curve between pull-up force and displacement under different working conditions;

[0008] S4: BP-RF machine learning algorithm is used for small sample data prediction;

[0009] S5: Compare and analyze the predicted results with the measured results, and determine the influence law of the pull-out force.

[0010] Furthermore, in step S1, the suction anchor pull-up visualization experimental device includes a suction anchor system, a reaction force frame and a control mechanism:

[0011] The suction anchor system comprises a hollow barrel suction anchor with a closed top and an open bottom. A pull rod is connected to the center of the anchor cover at the top of the hollow barrel, and the pull rod is connected to a driving mechanism. A tension sensor is installed on the pull rod, and the tension sensor is connected to a tension sensor data acquisition instrument. A drainage and exhaust hole with a valve is also provided on the anchor cover to discharge water and air trapped in the anchor during the sinking process. Before pulling up the suction anchor, the valve is closed to seal the drainage and exhaust hole.

[0012] The hollow drum is fixed in a glass box filled with sand and soil. The glass box is located in the reaction frame. The control mechanism is connected to the suction anchor system signal.

[0013] The tension sensor, the reaction force frame and the driving mechanism together constitute a loading system.

[0014] Furthermore, the sand is transparent soil; the reaction frame is welded from square steel pipes, which plays a role in stabilizing and transmitting the reaction force; the driving mechanism is a linear servo electric cylinder, which is used to stably provide different speeds to drive the pull rod to move, the pull rod lifting range is 0 to 300 mm, the pulling force range is 0 to 1000 N, the moving speed range is 1 to 500 mm / s, and the moving speed and lifting position can be adjusted through the touch panel on the control box; the control mechanism is a computer.

[0015] Furthermore, a threaded hole is provided at the center of the anchor cover for threaded connection with the pull rod.

[0016] Furthermore, the linear servo electric cylinder is connected to a guide rod, which is fixed to the top of the reaction frame and located above the suction bucket, and is used to control the relative position of the suction bucket in the sand.

[0017] Furthermore, step S2 is specifically as follows:

[0018] S2.1: Design working condition, the parameters that can be changed in the working condition include the inner diameter of the suction bucket, the outer diameter of the suction bucket, the length of the suction bucket and the upward pull force loading rate;

[0019] S2.2: Fill the prepared sand and soil into the plexiglass box;

[0020] S2.3: Use the driving mechanism to penetrate the suction anchor into the sand in the glass box;

[0021] S2.4: After the suction anchor penetrates the sand, let it stand for a while;

[0022] S2.5: Pull the suction anchor upwards and record the reading of the tension sensor;

[0023] S2.6: Use the control mechanism to perform data processing to further convert the curve of the tension on the tension sensor changing with time into a curve of the relationship between the pull-out tension and the displacement.

[0024] Furthermore, step S2.3 is specifically as follows: first, open the drainage valve on the suction anchor cover, adjust the position of the model box at the bottom of the suction anchor so that the suction anchor is at the plane center of the model box; second, use the driving mechanism to penetrate the suction anchor into the specified position in the sand.

[0025] Furthermore, in step S2.5, the method of pulling out the suction anchor is displacement control, and the pulling-up speed is controlled by a driving mechanism so that the suction anchor is pulled up at different loading rates, and the reading of the tension sensor is recorded by the control mechanism.

[0026] Furthermore, in step S3, the factors include: the barrel length of the barrel suction anchor, the barrel diameter of the barrel suction anchor and the pulling-up rate.

[0027] Furthermore, step S4 is specifically as follows:

[0028] S4.1: Create an input-output relationship table and set different factors as x i , forming the input matrix X;

[0029] S4.2: Map the input-output relationship table to the BP neural network model, and learn a mapping f through training NN (X)≈y, predicted output target;

[0030] S4.3: Mapping the input-output relationship table to a random forest (RF) model, and learning by training multiple decision trees; f RF (X)≈y, predict the input target;

[0031] S4.4: Perform weighted fusion on the prediction results of the BP neural network model and the random forest model to obtain the final prediction result.

[0032] Furthermore, the mathematical model of BP neural network is:

[0033]

[0034] X=[x1,x2,x3] T : Input vector, representing different factors in the database;

[0035] W1,W2: weight matrix;

[0036] b1, b2: bias vector;

[0037] g(): activation function (such as ReLU);

[0038] f(): output layer function (such as linear activation);

[0039] Furthermore, the random forest (RF) mathematical model is:

[0040]

[0041] T i (X) represents the i-th decision tree for input X = [x1, x2, x3] T The predicted value of; N is the total number of decision trees.

[0042] Furthermore, in step S4.4, the weighted fusion formula is:

[0043]

[0044] Where, α∈[0,1]: hybrid weight, reflecting the contribution of the two models. The value of α can be adjusted to find the best value through the validation set; f NN (X) is the prediction result of BP neural network; f RF (X) is the prediction result of random forest.

[0045] Furthermore, in step S5, the predicted results are compared with the measured results, the influence trend of different factors on the pull-out force is analyzed, and the influence law of the pull-out force is comprehensively determined by using image analysis and machine learning methods.

[0046] Furthermore, the suction anchor pull-up visualization experimental device also includes a camera and a laser mechanism arranged outside the reaction frame, the camera is located outside the reaction frame and faces the glass box; the camera is connected to the computer via a cable; the laser mechanism includes a laser emitter, a straight line lens and a laser power supply group, the power supply group is connected to the laser emitter cable, the laser emitter faces the straight line lens, and the straight line lens faces the glass box.

[0047] Compared with the prior art, the advantages of the present invention are:

[0048] 1. Taking into account the limitations of experimental equipment and conditions, the present invention aims at a small sample database, integrates the advantages of BP neural network algorithm and RF algorithm in processing small sample problems, and establishes a BP-RF hybrid machine learning method. Based on this method, a suction bucket pull-out bearing capacity prediction model is established, thereby exploring the influence of suction bucket length, diameter and pull-out rate on the pull-out bearing capacity, which provides a reference for the design of suction bucket pull-out bearing capacity.

[0049] 2. The present invention adopts a hybrid machine learning method to comprehensively consider various factors to predict the pull-out bearing capacity, and explains the pull-out bearing capacity by controlling a single variable, and explains the law of the pull-out bearing capacity of the suction bucket from the perspective of a single factor and multiple factors coupling.

[0050] 3. The present invention establishes a suction anchor pull-out visualization test device, conducts suction anchor pull-out experiments under different factors, and uses experimental data as a machine learning sample library, thereby avoiding the disadvantage that the prediction results are inconsistent with the actual results caused by using numerical simulation results as a sample library. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A schematic diagram of a flow chart of a method for predicting the pull-out bearing capacity of a suction bucket proposed in an embodiment of the present invention;

[0052] Figure 2 Schematic diagram of a suction anchor pull-out visualization test device in an embodiment of the present invention;

[0053] Figure 3 It is a schematic diagram of the cross-sectional structure of the suction bucket of the suction anchor in an embodiment of the present invention;

[0054] Figure 4 A comparison chart of the BP-RF prediction results obtained by the method of the embodiment of the present invention and the measured data;

[0055] Figure 5 is a graph showing the relationship between the pull-out force and the loading rate of the suction anchor obtained by the method of the embodiment of the present invention;

[0056] Figure 6 The figure is a relationship diagram between the pull-out force and the aspect ratio of the suction anchor obtained by the method of the embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be further described below.

[0058] This embodiment proposes a method for predicting the pull-out bearing capacity of a suction bucket. Figure 1 As shown, the method comprises the following steps:

[0059] S1: Establish a visual experimental device for suction anchor pull-out;

[0060] The suction anchor pull-up visualization experimental device includes a suction anchor system and a loading system. Figure 2 As shown, the loading system includes a tension sensor 5, a reaction frame 9 and a linear servo electric cylinder 6, and the suction anchor system includes a hollow thin-walled cylinder suction anchor 2 with a closed top and an open bottom. The hollow cylinder suction anchor 2 is made of a series of acrylic organic glasses, such as Figure 3As shown, a level 23 and a drainage and exhaust hole 21 with a valve are provided on the top anchor cover, which are used to discharge water and air trapped in the anchor during the sinking process. Before pulling up the suction anchor 2, the valve is closed to seal the drainage and exhaust hole 21; in addition, a threaded hole 22 with a diameter of 8 mm is drilled at the center of the anchor cover, and a pull rod is connected through the threaded hole. The pull rod is connected to the linear servo electric cylinder 6 through a flange 4. The linear servo electric cylinder 6 is used to stably provide different speeds to drive the pull rod to move. The lifting range of the pull rod is 0 to 300 mm, the tension range is 0 to 1000 N, and the moving speed range is 1 to 500 mm / s. The moving speed and lifting position can be adjusted through the touch panel on the control box; the tension sensor 5 is fixedly installed between the pull rod and the output end of the linear servo electric cylinder 6. The tension sensor 5 is also connected to the tension sensor data acquisition instrument 8 through a cable to collect tension values.

[0061] The hollow barrel suction anchor 2 is located in an acrylic organic glass box 1, and the glass box 1 is filled with transparent soil 3. The hollow barrel suction anchor 2 is penetrated into the transparent soil 3 in the acrylic organic glass box 1 by a linear servo electric cylinder 6, and the linear servo electric cylinder 6 is connected to a guide rod 7. Figure 2 As shown, the guide rod 7 is fixed to the top of the reaction frame 9, located above the suction anchor 2, and is used to control the relative position of the hollow barrel suction anchor 2 in the transparent soil 3. The glass box 1 is placed in the metal reaction frame 9. In this embodiment, the reaction frame 9 is welded by square steel pipes and plays a role in stabilizing and transmitting the reaction force; the suction anchor system is connected to the microcomputer 11 signal.

[0062] In addition, a camera 10 and a laser mechanism are provided outside the reaction frame 9, wherein the camera 10 is located outside the side of the reaction frame 9, facing the side of the glass box 1, and is connected to the microcomputer 11 through a cable transmission; the laser mechanism includes a laser emitter 12, a straight line lens 13 and a laser power supply group 14, such as Figure 2 As shown, the laser power supply group 14 is connected to the laser emitter 12 by cable, the laser emitter 12 is facing the straight line lens 13, and the straight line lens 13 is facing the front of the glass box 1.

[0063] In this embodiment, the internal clearance dimensions of the acrylic organic glass box 1 are 18 cm×18 cm×40 cm in length, width and height respectively, and the wall thickness is 1 cm.

[0064] In this embodiment, the five suction anchors 2 selected are respectively recorded as M-1, M-2, M-3, M-4, and M-5, and their size parameters, average diameter D, length L, suction bucket side wall thickness t1, and suction bucket top wall thickness t2, are respectively shown in Table 1:

[0065] Table 1 Selected suction anchor parameters

[0066]

[0067] S2: Using the above experimental device, the suction anchor pull-up test under different working conditions is carried out, and the relationship curve between the pull-up force and the displacement under different working conditions is obtained through data processing, specifically:

[0068] S2.1: Design working condition, the parameters that can be changed in this working condition include the inner diameter of the suction bucket, the outer diameter of the suction bucket, the length of the suction bucket and the upward pull force loading rate;

[0069] S2.2: Fill the prepared transparent soil 3 into the acrylic glass box 1;

[0070] S2.3: Use the linear servo electric cylinder 6 to penetrate the suction anchor 2 into the transparent soil 3 in the glass box; the specific process of this step is: first, open the drainage valve on the anchor cover of the suction anchor 2, and adjust the position of the glass box 1 at the bottom of the suction anchor so that the suction anchor 2 is in the plane center of the glass box; secondly, use the linear servo electric cylinder 6 to penetrate the suction anchor 2 into the specified position in the transparent soil 3 in the glass box 1.

[0071] S2.4: After the suction anchor 2 penetrates the transparent soil 3, it is left to stand for a period of time;

[0072] S2.5: After standing still, the suction anchor 2 is pulled upward, and the reading of the tension sensor is recorded; wherein, the method of pulling the suction anchor 2 is displacement control, and the pulling speed is controlled by the linear servo electric cylinder 6, so that the suction anchor 2 is pulled upward at different loading rates, and the reading of the tension sensor is collected by the tension sensor data acquisition instrument 8 and transmitted to the microcomputer 11.

[0073] In this embodiment, the tension sensor 5 used has a range of 500N and an accuracy of 0.01N, and the sampling frequency of the tension data acquisition instrument 8 is 10Hz. The loading rate records of the above five suction anchors are shown in Table 2 below:

[0074] Table 2 Record of pull-up loading rate of different suction anchors

[0075]

[0076] S2.6: Using the microcomputer 11, data processing is performed to further convert the curve of the tension on the tension sensor changing with time into a curve of the relationship between the pull-out tension and the displacement.

[0077] S3: Based on the relationship curve between the pull-out force and the displacement under different working conditions, a suction bucket "factor-pull-out force" database is generated, wherein the specific factors include: the barrel length of the barrel suction anchor, the barrel diameter of the barrel suction anchor and the pull-out rate.

[0078] In this embodiment, part of the database is shown in Table 3 below:

[0079] Table 3 “Factor-uplift force” database (partial)

[0080]

[0081] S4: Use BP-RF (neural network-random forest) machine learning algorithm to predict small sample data. The method is:

[0082] S4.1: Create an input-output relationship table and set different factors as x i , forming the input matrix X;

[0083] S4.2: Map the above input-output relationship table to the BP neural network model. The mathematical model of the BP neural network is:

[0084]

[0085] X=[x1,x2,x3] T : Input vector, representing different factors in the database;

[0086] W1,W2: weight matrix;

[0087] b1, b2: bias vector;

[0088] g(): activation function (such as ReLU);

[0089] f(): output layer function (such as linear activation);

[0090] Learn a mapping f through training NN (X)≈y, predicted output target;

[0091] S4.3: Map the above input-output relationship table to a random forest (RF) model. The mathematical model of the random forest (RF) is:

[0092]

[0093] T i (X) represents the i-th decision tree for input X = [x1, x2, x3] T The predicted value; N is the total number of decision trees

[0094] Learn f by training multiple decision trees RF (X)≈y, predict the input target;

[0095] S4.4: Perform weighted fusion on the prediction results of the BP neural network model and the random forest model to obtain the final prediction result. The weighted fusion formula is:

[0096]

[0097] Where, α∈[0,1]: hybrid weight, reflecting the contribution of the two models. The value of α can be adjusted to find the best value through the validation set; f NN (X) is the prediction result of BP neural network; f RF (X) is the prediction result of random forest.

[0098] S5: Compare the predicted results with the measured results, analyze the influence trend of different factors on the pull-out force, and use image analysis and machine learning methods to comprehensively judge the influence law of the pull-out force.

[0099] In this embodiment, the predicted results and the measured results are compared. Figure 4 As shown, from Figure 4 It can be seen that the closer the scattered points are to the ideal line, the more accurate the prediction results of the BP-RF model are.

[0100] In this embodiment, the model evaluation index R is calculated. 2 =0.81, calculate the mean of the sum of squares of the errors between the predicted value and the true value MSE = 5579, where R 2 Measures the proportion of the variance of the target variable explained by the model, from R 2 The calculation results show that the model is highly accurate. The MSE value is too large because the measured data fluctuates greatly, the data sample is small, and the predicted value y itself is on the order of 10 2 Therefore, from the experimental point of view, considering the large indicators of the model, the BP-RF model can better predict the pull-out bearing capacity of the suction bucket caused by different factors. The following will use image analysis to explain the influence trend of different factors on the pull-out bearing capacity from the perspective of controlling a single variable.

[0101] The influence of suction anchor length on the pull-out force is as follows: Figure 5 (a) shows that the influence of the suction anchor diameter (suction anchor cross section) on the pull-out force is shown in Figure 5 (b) shows that the two rules are significantly different. In comparison, the suction anchor diameter (cross-sectional area of ​​the anchor) has a more significant effect on the bearing capacity of the suction anchor foundation. When the pull-up rate is low (v = 1 mm / s), the difference between the anchor length and the anchor diameter on the bearing capacity is not obvious. When the anchor is pulled up at a high speed, the anchor diameter plays a dominant role in the bearing capacity, that is, the negative pressure at the top provides most of the pull-up resistance.

[0102] Figure 6 (a) and Figure 6 (b) shows the relationship between the pull-out force and loading rate for different suction anchor length-to-diameter ratios L / D:

[0103] Figure 6 (a) shows the relationship between the uplift force and the uplift rate when the diameter of the suction anchor is fixed at D = 50 and the length-diameter ratios L / D are 0.5, 1, and 1.5 respectively. From Figure 6 (a), it can be seen that when the diameter of the suction anchor is fixed, as the length-diameter ratio L / D increases, the uplift force of the suction anchor also continuously increases, and when v < 25 mm / s, the slope of the curve also continuously increases.

[0104] Figure 6 (b) shows the relationship between the uplift force and the uplift rate when the length of the suction anchor is fixed at L = 50 and the length-diameter ratios L / D are 0.83, 1, and 1.25 respectively. From Figure 6 (b), it can be seen that when the length of the suction anchor is fixed, as the length-diameter ratio L / D increases, the uplift force of the suction anchor continuously decreases;

[0105] From Figure 6 (a) and Figure 6 (b), it can be seen that the uplift force of the suction anchor first increases and then basically remains unchanged as the loading rate increases, and the relationship between the two is a non-linear relationship. When the uplift rate v of the suction anchor < 25 mm / s, the growth rate of the curve is relatively fast; when the uplift rate 25 mm / s < v < 100 mm / s, the growth rate of the curve decreases; when the uplift rate v > 100 mm / s, the curve basically remains unchanged. This is because as the loading rate increases, the failure mode of the suction anchor foundation changes.

[0106] The above are only the preferred embodiments of the present invention and do not impose any limitation on the present invention. Any person skilled in the art within the technical field, without departing from the technical solution of the present invention, makes any form of equivalent substitution or modification and other changes to the technical solution and technical content disclosed by the present invention, all of which belong to the content not departing from the technical solution of the present invention and still fall within the protection scope of the present invention.

Claims

1. A method for predicting the pull-out bearing capacity of a suction bucket, characterized in that: The steps include: S1: Establish a visual experimental device for suction anchor pull-out; S2: Using the experimental device, the suction anchor pull-out test under different working conditions is carried out, and the relationship curve between the pull-out force and the displacement under different working conditions is obtained through data processing; S3: Generate a suction bucket "factor-pull force" database based on the relationship curve between pull-up force and displacement under different working conditions; S4: BP-RF machine learning algorithm is used for small sample data prediction; S5: Compare and analyze the predicted results with the measured results, and determine the influence law of the pull-out force.

2. The method for predicting the pull-out bearing capacity of a suction bucket according to claim 1, characterized in that: In step S1, the suction anchor pull-up visualization experimental device includes a suction anchor system, a reaction force frame and a control mechanism: The suction anchor system comprises a hollow barrel suction anchor with a closed top and an open bottom. A pull rod is connected to the center of the top anchor cover of the hollow barrel, and the pull rod is connected to a driving mechanism. A tension sensor is installed on the pull rod, and the tension sensor is connected to a tension sensor data acquisition instrument. A drainage and exhaust hole with a valve is also opened on the anchor cover. The hollow drum is fixed in a glass box filled with sand and soil. The glass box is located in the reaction frame. The control mechanism is connected to the suction anchor system signal.

3. The method for predicting the pull-out bearing capacity of a suction bucket according to claim 2 is characterized in that: The sand is transparent soil; the reaction frame is welded from square steel pipes; the driving mechanism is a linear servo electric cylinder, which is used to provide different speeds to drive the pull rod to move, the pull rod lifting range is 0 to 300 mm, the pulling force range is 0 to 1000 N, and the moving speed range is 1 to 500 mm / s; the control mechanism is a computer.

4. The method for predicting the pull-out bearing capacity of a suction bucket according to claim 2, characterized in that: Step S2 is specifically as follows: S2.1: Design working condition, the parameters that can be changed in the working condition include the inner diameter of the suction bucket, the outer diameter of the suction bucket, the length of the suction bucket and the upward pull force loading rate; S2.2: Fill the prepared sand and soil into the plexiglass box; S2.3: Use the driving mechanism to penetrate the suction anchor into the sand in the glass box; S2.4: After the suction anchor penetrates the sand, let it stand for a while; S2.5: Pull the suction anchor upwards and record the reading of the tension sensor; S2.6: Use the control mechanism to perform data processing to further convert the curve of the tension on the tension sensor changing with time into a curve of the relationship between the pull-out tension and the displacement.

5. The method for predicting the pull-out bearing capacity of a suction bucket according to claim 4 is characterized in that: In step S2.5, the method of pulling the suction anchor is displacement control, and the pulling speed is controlled by the driving mechanism, and the suction anchor is pulled up at different loading rates.

6. The method for predicting the pull-out bearing capacity of a suction bucket according to claim 1, characterized in that: In step S3, the factors include: barrel length of the barrel suction anchor, barrel diameter of the barrel suction anchor and pulling-up speed.

7. The method for predicting the pull-out bearing capacity of a suction bucket according to claim 1, characterized in that: Step S4 is specifically as follows: S4.1: Create an input-output relationship table and set different factors as x i , forming the input matrix X; S4.2: Map the input-output relationship table to the BP neural network model, and learn a mapping f through training NN (X)≈y, predicted output target; S4.3: Mapping the input-output relationship table to a random forest model, and learning by training multiple decision trees; f RF (X)≈y, predict the input target; S4.4: Perform weighted fusion on the prediction results of the BP neural network model and the random forest model to obtain the final prediction result.

8. The method for predicting the pull-out bearing capacity of a suction bucket according to claim 7, characterized in that: In step S4.4, the weighted fusion formula is: Where, α∈[0,1]: hybrid weight, reflecting the contribution of the two models. Adjusting the value of α can find the optimal value through the validation set; f NN (X) is the prediction result of BP neural network; f RF (X) is the prediction result of random forest.

9. The method for predicting the pull-out bearing capacity of a suction bucket according to claim 1, characterized in that: In step S5, the predicted results are compared with the measured results, the influence trend of different factors on the pull-out force is analyzed, and the influence law of the pull-out force is comprehensively judged by using image analysis and machine learning methods.

Images